Papers

In this paper, we investigate a multi-cell six-dimensional movable antenna (6DMA) network for enhancing downlink communication performance under inter-cell interference (ICI). Each base station (BS) is equipped with multiple 6DMA surfaces, and the 6DMA rotations affect both the desired-signal enhancement for in-cell users and the interference leakage toward neighboring cells, which makes the antenna-rotation design and transmit precoding intrinsically coupled across BSs. To address this issue, we formulate an average weighted sum-rate maximization problem for the multi-cell system by jointly optimizing the short-term downlink precoders and long-term 6DMA rotations under practical antenna geometric constraints. To tackle the resulting nonconvex problem, we propose a distributed two-timescale design based on inter-cell interference power constraint (IPC) coordination among neighboring BSs, under which each BS performs local short-term precoder optimization based on instantaneous channel state information (CSI) and long-term 6DMA rotation update according to statistical CSI with limited inter-BS information exchange. In particular, an edge-wise IPC coordination mechanism based on two-stage one-dimensional grid search and random maximal matching is developed to enable scalable distributed implementation. A centralized offline benchmark is also provided for performance comparison. Numerical results show that the proposed distributed design achieves performance close to the centralized benchmark under different interference conditions, while maintaining favorable scalability as the network size increases.

Audio context determines which sound components and sources are relevant and which can be perceived as irrelevant (noise) by listeners. For example, traffic noise is informative in urban surveillance but noise for a phone call at the same location. Most current audio denoising systems apply fixed target-noise definitions, often removing useful components in one context while failing to suppress irrelevant components. To address this, we introduce the concept automatic contextual audio denoising (ACAD) which defines target and noise based on the inferred context. In this work, we restrict context to be associated with an acoustic scene class. We label sound events outside the event distribution of a scene class (noise) as out-of-context (OC) and events typical for that scene as in-context (IC). We implement a deep learning method that automatically infers the context of the audio signal and removes OC components, and benchmark it against variants: without context inference, with oracle context, and with separately provided uninformative context. On paired clean/noisy data across diverse contexts, where OC components in one context may be IC in another, our proposed method outperforms other approaches across standard objective metrics, indicating that the model can infer context and context-dependent processing can enhance denoising.

We study online optimization problems in which the cost function depends on latent, time-varying parameters that are unmeasurable and governed by unknown dynamics. Specifically, we consider a strongly convex cost function whose linear term evolves according to unknown linear stochastic dynamics about an unknown nominal operating point, while the algorithm has access only to finite noisy gradient measurements. We propose a solution that uses control theoretic tools to reconstruct the latent parameters from gradient observations using a Gauss-Markov estimator, then identifies the parameter dynamics using a bias-reduced instrumental variable estimator, and finally forecasts the parameters to compute the minimizer. We provide a high probability, finite-horizon bound on the expected tracking error. We illustrate our algorithm on a series of numerical examples.

Safety has been a major concern when deploying deep reinforcement learning algorithms in the real world. A promising direction that ensures that the learned policy does not visit unsafe regions is to learn a barrier function along with the policy. A barrier is a function from states to reals that assigns low values to the initial states, high values to the unsafe states, and decreases in expectation on each transition; such a function can be used to bound the probability of reaching unsafe states. Previous attempts learned a barrier function directly from exploration data, but this required either large amounts of data or restrictions on the system dynamics. In this paper, we show how kernel embeddings can be used to learn barrier functions during deep reinforcement learning for stochastic systems with unknown dynamics. Our algorithm, kernel-based safe exploration (KBSE), learns an optimal policy and a barrier simultaneously during exploration. The barriers are computed iteratively, represented as conditional mean embeddings, and provide better probabilistic safety guarantees with more exploration. The exploration algorithm uses the learned barrier functions to identify safety violations. In the case of violation, it intervenes to modify the unsafe action to a safe action, thereby ensuring that the exploration is restricted to actions that bound the probability of reaching unsafe states. We evaluate KBSE on several complex continuous control benchmarks. Experimental results establish our new algorithm to be suitable for synthesizing control policies that are probabilistically safe without degradation in reward accumulation.

Renewable-driven microgrids dominated by grid-forming (GFM) converters are subject to persistent power fluctuations, making equilibrium-known stability assessments restrictive. This paper develops an equilibrium-free contraction stability method based on semi-contraction theory. By formulating the system in a symmetry-aware projected state space, the intrinsic rotational mode induced by uniform angle shifts is removed. A blockwise Jacobian decomposition is introduced to characterize the coupled active and reactive power dynamics, yielding a computable regional contraction condition. This condition is then converted into forward-invariant stability certificates that provide trajectory-level performance guarantees. For autonomous operation without disturbances, the method provides an equilibrium-free nonlinear stability characterization together with an estimation of the region of attraction (ROA). For non-autonomous operation under disturbances, it derives explicit bounds for quasi-steady tracking under slowly varying injections and for robustness under fast or composite disturbances. Case studies on a 9-bus system validate the proposed method.

User-defined keyword spotting (KWS) is crucial for personalized voice interaction, yet existing methods face several challenges: (1) insufficient discriminability among confusable words, (2) performance inconsistency across speakers with varying pronunciations, and (3) high data cost to ensure reliable wake-word performance. In this paper, we introduce DMA-KWS, an efficient and robust framework for user-defined keyword spotting. First, it adopts a dual-stage matching pipeline: CTC decoding with streaming phoneme search to locate candidate segments, followed by QbyT with a phoneme matcher for fine-grained verification, enabling it to better distinguish confusable words. Next, multi-modal enrollment fuses user-specific speech with text embeddings to further improve accuracy for registered users. Finally, a parameter-efficient continual adaptation mechanism performs lightweight updates using synthetic and real data. Extensive experiments demonstrate the superior performance of DMA-KWS. On the LibriPhrase Hard subset, it achieves 97.85% AUC and 6.13% EER, reaching state-of-the-art performance. In speaker-dependent settings, DMA-KWS consistently outperforms text-only enrollment, demonstrating significant performance gains. Moreover, the proposed parameter-efficient fine-tuning mechanism adapts DMA-KWS with only 187k updated parameters, further enhancing KWS performance while ensuring suitability for on-device deployment.

Extremely large aperture arrays (ELAAs) and millimeter-wave (mmWave) technologies are essential for achieving high data rates in future wireless communication systems. To perform precise beamforming, these systems require accurate channel estimation, in which the near-field wavefront curvature effect must be taken into account. Existing channel estimation methods rely on the spherical wavefront channel (SWC) model, which is suitable for near-field propagation with point sources, scatterers, and reflection planes. However, when a near-field curved reflecting surface exists, the wavefront of the reflected wave becomes anisotropic rather than spherical, causing the SWC model to become inaccurate. To address this problem, in this paper, we formulate a parameterized model for the anisotropic wavefront channel (AWC). Using this model, we propose a channel estimation algorithm based on physical parameter recovery for the AWC. Simulation results reveal that the AWC no longer retains sparsity in the angle-distance domain. Furthermore, the results demonstrate how different physical characteristics of the propagation scenario affect the degree of wavefront anisotropy, and confirm the effectiveness of our proposed algorithm in AWC scenarios.

This paper addresses bearing-only algorithms for solving the Fermat-Weber Location Problem (FWLP) with a unicycle agent. Unlike existing FWLP solutions for single- or double-integrator agents, our approach accounts for the nonholonomic constraints of wheeled robots. We first develop a bearing-only control law for the case with stationary beacons. Next, we consider saturated control inputs and propose a corresponding bearing-only control law. Finally, we address moving beacons with constant velocities and develop a control law that enables the unicycle agent to track the moving Fermat-Weber point. Both simulations and experiments are provided to demonstrate the effectiveness of the proposed methods.

Since the beam squint and near-field effects both inherently exist in upper-6 GHz (U6G) extremely large-scale multiple-input multiple-output (XL-MIMO) systems, wideband near-field channel estimation faces severe challenges, such as higher computational complexity, and higher pilot overhead particularly at hybrid architectures with fewer radio frequency (RF) chains. To precisely reduce the complexity and number of pilots, the parametric symmetry of wideband near-field channels is explored, such that the channel parameters, including angle, distance, and range, can be decoupled based on the delay variations observed by different antennas. Based on this, a distributed parametric symmetry-based (DPS) algorithm, applicable to U6G XL-MIMO, is proposed. The delays observed by different subarrays are estimated and extrapolated across the local processing units (LPUs) firstly, and then, the channel parameters are decoupled and estimated at the central processing unit (CPU), by only linearly combining the delays from different LPUs. The path gains are calculated at different LPUs, respectively, to reconstruct the channel with low complexity. Since the proposed algorithm does not rely on scanning the polar-domain dictionary, only a single pilot is required even with hybrid architectures. Furthermore, the computational complexity, multiple-path resolution, Cramer-Rao lower bound (CRLB) and lower bound (LB) of the estimates in hybrid architectures and the DPS algorithm, respectively, are analyzed, to evaluate the realizable potential of the proposed algorithm. The simulation results prove that the proposed algorithm has a higher estimation accuracy, while requiring less complexity and pilots.

While flow-matching text-to-speech (TTS) achieves strong zero-shot speaker similarity and naturalness, it remains susceptible to content fidelity issues, particularly skip and repeat errors from imperfect alignment. We propose RobustSpeechFlow, a training strategy that improves alignment robustness by extending contrastive flow matching with length-preserving repeat and skip latent augmentations. Requiring no external aligners or preference data, our method directly penalizes realistic failure modes and readily integrates into existing pipelines. On Seed-TTS-eval, it reduces the word error rate (WER) from 1.44 to 1.38 using only 0.06B parameters. On our ZERO500 benchmark, it delivers consistent intelligibility improvements across diverse speaker and prosody conditions; at NFE=24, it reduces English character error rate (CER) from 0.48% to 0.35% and Korean CER from 0.81% to 0.57%. Audio samples: https://robustspeechflow.github.io/

This paper investigates the joint optimization of power allocation and antenna activation in sparse extremely large aperture array systems operating under power amplifier non-linearities. We first derive an analytical expression for the achievable spectral efficiency (SE) of point-to-point MIMO channels affected by non-linear distortions using the Bussgang decomposition. To address the combinatorial and non-convex nature of the energy-efficiency (EE) maximization problem, we employ an unsupervised deep neural network (DNN) that learns the non-linear mapping between the channel state information and the optimal EE operating point. The DNN jointly predicts distortion-aware power allocation, total transmit power scaling, and modular sub-array activation based on singular-value and geometric channel features. Numerical results demonstrate that the proposed DNN-based arrays achieve significant EE gains over the conventional sparse arrays.

In modern industrial systems, machinery frequently operates under dynamic environments with continuously varying loads and speeds. Consequently, deep learning-based fault diagnosis models often suffer from severe performance degradation under unseen operating conditions due to complex data distribution shifts. Since existing methods predominantly rely on static offline training, they lack the capability to dynamically adapt to these continuous variations. To address this issue, an integrated framework combining offline domain generalization (DG) and online test-time adaptation (OTTA) is proposed. Initially, a model with preliminary generalization capability is obtained offline by extracting domain-invariant features via adversarial learning. During the online phase, a dual-memory replay mechanism is developed. By selectively storing high-confidence online pseudo-labeled samples and replaying them with historical offline data, the model facilitates adaptation to changing data distributions and helps reduce forgetting of previously learned knowledge Experiments on a real-world motor dataset show that the proposed approach achieves competitive performance under the considered unseen operating conditions.

Accurate and robust medical image classification is paramount for early disease diagnosis and treatment planning. However, challenges such as limited annotated data, high intra-class variability, and subtle inter-class differences often hinder the performance of deep learning models. This paper introduces a synergistic deep learning framework that leverages the strengths of self-supervised learning and transfer learning for enhanced medical image classification. Our approach employs two distinct ConvNeXt-Tiny models: one pre-trained on a large-scale natural image dataset (ImageNet) and another pre-trained using an entropy-guided Masked Autoencoder (MAE) on the target medical dataset. Both models are then fine-tuned on specific medical image classification tasks. A final ensemble strategy, based on averaging predicted probabilities, is utilized to combine the complementary insights from these two models. Rigorous experimental validation across four diverse medical imaging datasets (Breast Ultrasound Images (BUSI), International Skin Imaging Collaboration (ISIC) 2018, Kvasir, and COVID) demonstrates the superior performance and robustness of our ensemble approach. The MAE pre-training significantly improves feature learning on domain-specific data, while the ImageNet pre-training provides strong generalizable features. The ensemble consistently achieves state-of-the-art results, outperforming individual models and existing methods, highlighting the efficacy of combining diverse pre-training strategies for challenging medical image analysis.

The integration of machine learning with domain-specific physics is transforming the design, monitoring, and control of electricity systems, where data scarcity, limited interpretability, and the need to enforce physical laws constrain purely data-driven models. Physics-informed machine learning (PIML) addresses these limitations by embedding governing equations directly into the learning process, yielding accurate, efficient, and scalable solutions for Industry 4.0 applications. This article reviews hybrid PIML architectures for electricity systems, including physics-informed neural networks (PINNs), Deep Operator Networks (DeepONets), Fourier Neural Operators, Extreme Learning Machine-enhanced PINNs, graph-based PINNs (PIGNNs), and domain-decomposition PINNs. Each approach is examined through case studies spanning field analysis, fault detection, digital twins, surrogate modeling, and control optimization. The review shows that embedding Maxwell's equations and other first-principles constraints substantially improves predictive accuracy under sparse and noisy data, reduces simulation time by orders of magnitude relative to finite element methods, and enhances generalization across operating regimes. Hybrid frameworks consistently outperform purely data-driven baselines on parameter sensitivity, dynamic behavior, and robustness, while supporting real-time digital-twin calibration and uncertainty quantification. Persistent challenges include training instability for stiff multi-scale problems, computational cost of high-fidelity models, and the absence of standardized benchmarks. The findings demonstrate that PIML enables a paradigm shift from black-box data-driven methods to transparent, physics-informed strategies, positioning the field for sustained innovation in resilient and intelligent electricity systems.

The highly dynamic nature of vehicular networks necessitates proactive and site-specific radio resource management (RRM) to achieve ultra-reliable low-latency communications. While Network Digital Twins (NDTs) have emerged as a promising enabler, ray-tracing remains time-consuming, challenging accurate RRM under latency constraints. We propose AdaPTwin, an adaptive multi-fidelity predictive NDT for proactive and latency-aware RRM in vehicular networks. Unlike single- and multi-fidelity NDTs with fixed fidelity levels, AdaPTwin dynamically adjusts NDT fidelity based on network conditions. The framework adopts a hierarchical cloud-edge architecture, where computationally intensive fidelity selection is performed periodically in the cloud, and the proactive RRM loop operates in real-time at the edge. The edge-based proactive RRM task consists of channel prediction between vehicles and roadside units (RSUs) via trajectory forecasting and look-ahead ray tracing, followed by RRM execution. A transformer model enhanced with continual and transfer learning enables vehicular trajectory prediction while adapting to new environments and traffic patterns. Ray-tracing is performed using NVIDIA Sionna by exploiting a dynamically updated virtual environment to ensure realistic radio propagation within the NDT. Furthermore, a joint RSU beamforming and vehicle-RSU association problem is formulated to maximize proportionally fair sum-rate, and it is efficiently solved using a scalable multi-start iterative coordinate descent algorithm. Comparisons against reactive, single-fidelity, and non-adaptive predictive NDTs under realistic vehicular conditions confirm that AdaPTwin successfully adapts to diverse scenarios where other frameworks fail. Ultimately, AdaPTwin achieves up to 90% sum-rate gain and 80% outage probability reduction compared to non-adaptive NDTs, while maintaining real-time performance.

In this letter, we propose a new wireless sensing system equipped with a rotatable antenna (RA) array to enhance the sensing performance of a uniform sparse array (USA). To tackle the severe spatial undersampling issues, we propose a novel tensor decomposition-based direction-of-arrival (DOA) estimation algorithm. Specifically, we introduce a synchronous multiple rotation pattern for active target probing such that the received signals across multiple rotations to capture the diverse spatial degree of freedoms. Subsequently, we mathematically formulate the received signals across successive rotations as a third-order tensor, and leverage the canonical polyadic decomposition to obtain the factor matrices incorporating the DOA of targets. By analyzing the extrema distribution laws of array steering vector correlation (SVC) and gain SVC of RAs, we propose to combine the array and gain factor matrices via the Kronecker product, which theoretically guarantees the unambiguous DOA estimation. Simulation results demonstrate that the proposed RA-enhanced tensor decomposition-based algorithm achieves high-precision and unambiguous sensing performance compared to conventional uniform dense arrays and omnidirectional antenna systems.

Orbital debris is a pressing problem which presents a danger to global space operations and a barrier to continued development of the space economy and space infrastructure. As research continues regarding orbital debris, there is a need for tools to understand the system-level implications of orbital debris solutions. This research considers the orbital debris problem as a dynamic process. Based on dynamic system theories, time-series variables of the numbers of orbital debris, orbital objects, and object launches should be causally linked, which means they share a common system attractor manifold. We propose a data-driven method based on complexity science to reconstruct a shadow attractor of the dynamic system using limited observable variables. The reconstructed shadow attractor helps us to understand the fundamental system dynamics for orbital debris and enables us to simulate the future of the orbital debris system based on changes to policy. These findings represent a significant advancement in our ability to understand high level impacts of space system policy with limited data available.

Coordinate-conditioned neural networks can generate head-tracked personal sound zone (PSZ) loudspeaker filters in real time, but they are sensitive to localization uncertainty. Small fluctuations in estimated listener coordinates, caused by optical distortion, temporary occlusions, or tracking jitter, may produce large filter changes even when listeners are physically stationary. This paper proposes neighbor-consistent neural filters that regularize the coordinate-to-filter mapping by penalizing filter differences at randomly perturbed neighboring coordinates during training. To evaluate robustness against tracking noise, we introduce a decoupled protocol that fixes the acoustic transfer functions at a physical anchor while perturbing only the coordinate inputs used for filter generation. Isolation quality and local stability are evaluated using neighborhood median and lower-tail statistics of inter-zone and inter-program isolation, together with spatial variation rates that quantify metric sensitivity within a coordinate neighborhood. In simulation with a split-band woofer-tweeter system and 25 randomly sampled anchor positions, neighbor consistency reduces the root-mean-square (RMS) variation rate by up to 55.9% in the woofer band and 30.3% in the tweeter band while largely preserving isolation quality and improving lower-tail robustness. In in-situ measurements using a 24-driver array and two stationary head-and-torso simulators, the proposed regularization improves worst-case neighborhood isolation by up to 16.9% and reduces spatial variation rates by up to 61.8%. These results demonstrate that neighbor-consistency regularization effectively stabilizes PSZ rendering under localization uncertainty.

Objective: Conventional urodynamics (UDS) provide critical diagnostic information, but requires invasive dual catheterization and manual labeling of clinically important events. Wireless, catheter-free bladder function tests are becoming available for home use, but only provide vesical pressure (Pves). We developed a machine learning framework that was trained and externally validated on UDS data for automated urological event classification from single-channel (Pves) recordings. Methods: We analyzed 118 annotated UDS traces segmented into 0.8-second Pves intervals. Using the discrete wavelet transform, we extracted 55 statistical features per segment. Consecutive segments (233,338 segments; three classes) sharing the same class, abdominal (ABD), detrusor overactivity (DO), or voiding contraction (VOID), were grouped into events, and median feature aggregation was applied to derive event-level representations. Using an imbalanced dataset, we trained a two-stage multilayer perceptron (MLP): Stage 1 distinguished VOID vs non-VOID, and Stage 2 classified non-VOID into ABD and DO. The model was trained on two independent datasets and externally validated on a third independent dataset. Additional cross-dataset training-validation permutations were performed to assess generalizability. Performance was evaluated using accuracy, F1-macro, sensitivity, specificity, and area under the curve (AUC). Results: Stage 1 (VOID vs. non-VOID) achieved 84% accuracy (balanced accuracy 76%), F1-macro 0.74, and AUC 0.85, while Stage 2 (ABD vs. DO) reached 90% accuracy (balanced accuracy 80%), F1-macro 0.80, and AUC 0.87. Permutation feature importance indicated that most features contributed meaningfully. Conclusion: Our machine learning approach enables accurate automated detection of urological events from Pves, demonstrating feasibility for single-channel monitoring and future ambulatory applications.

Data leakage from API responses has drawn wide attention. APIs are often not fully regulated, making them easy to abuse. One common solution is to embed watermarks into API responses for traceability. However, existing watermarking methods often require modifying database content or API response data. This forces changes to business system code, and may even disrupt normal business operations because data values are altered. In this paper, we propose an original pluggable watermarking scheme based on a watermark proxy gateway and PEMark (Position Encoding-based Watermarking). The key novelty of our approach is exploiting the inherent permutation redundancy in the ordering of JSON/XML key-value pairs – an overlooked dimension that carries no semantic information yet provides abundant encoding capacity. First, we forward server responses to the watermark proxy gateway, a design that requires zero modification to existing business systems. Then, we embed a watermark into each API response using position encoding, which reorders keys without altering any data values. To the best of our knowledge, this is the first work to achieve distortion-free API response watermarking via position encoding over a proxy gateway. Our method does not modify any data values, so normal business operations continue seamlessly after watermark embedding. Experimental results show that our framework maintains business usability while ensuring that returned API data is traceable. Compared with current mainstream schemes, our method is robust against tampering and insertion attacks (100% similarity), and can withstand certain levels of deletion attacks.

Standard transformer attention computes pairwise similarity between queries and keys, treating all tokens as equally salient regardless of their intrinsic informational content. In turbulent fluid dynamics, coherent structures – the energetically dominant, spatially organized patterns that persist amid background chaos – carry a disproportionate fraction of total energy and govern all transport. We propose that tokens play an analogous role in transformer attention: informationally dense positions (morphological boundaries, syntactic heads, discourse markers) concentrate spectral energy and should attract proportionally more attention than background tokens (function words, repeated patterns, low-information filler). We propose Energy-Gated Attention (EGA): a simple modification that gates value aggregation by the spectral energy of key token embeddings, computed by a single learned linear projection that discovers the dominant spectral mode of the embedding field. On TinyShakespeare, EGA achieves +0.103 validation loss improvement with only 12,480 additional parameters (<0.26% overhead) and no measurable computational cost. The result is consistent on Penn Treebank (+0.101), demonstrating dataset independence. A systematic ablation across three wavelet families (fixed Morlet, Daubechies db2/db4, and a parametric Morlet) establishes that fixed structured bases are suboptimal – the optimal energy direction is data-adaptive and non-sinusoidal – while identifying learned wavelet packets as a promising open direction. The learned energy threshold converges to tau ~= 0.35 independently of initialization, corresponding to the fraction (~36%) of tokens carrying above-average spectral energy in English text, a stable linguistic property consistent with the fraction of content words in running English text.

LiDAR semantic segmentation is a core perception capability for autonomous vehicles and mobile robots. However, safe operation also depends on knowing when predictions are unreliable. Existing approaches typically rely on softmax confidence, which is often miscalibrated and overconfident, while stronger uncertainty estimates from Monte Carlo dropout or ensembles are often computationally expensive for real-time use. To this end, we introduce a novel, architecture-agnostic uncertainty-aware Adapter Head. It decomposes the prediction into a Preference Head for class ranking and a Strength Head that refines uncertainty assessment, thereby enabling a principled construction of evidential Dirichlet representations. Building on this design, we propose our inverse-vacuity self-calibration objective (Invascal), which directly supervises the strength signal to produce reliable and well-calibrated uncertainty estimates while preventing runaway evidence growth. We evaluate our framework across multiple LiDAR datasets and backbone architectures. We compare against deterministic training, Monte Carlo dropout and ensembles, and prior evidential methods. Our approach consistently improves uncertainty calibration over traditional deterministic methods with minimal computational overhead. At the same time, it preserves competitive segmentation accuracy, where prior evidential methods often suffer performance degradation.

Diffusion and flow-matching based text-to-speech (TTS) models excel in naturalness but often lack explicit emotion control, as emotional signals remain entangled with speaker identity. We discover that emotion embedding emerges as a linearly decodable direction of frozen hidden states, nearly orthogonal to the direction embedding speaker identity. This inspires a plug-and-play framework DUET for emotion control over pretrained diffusion and flow-matching based TTS models. During generation, DUET unifies dual-space control to achieve fine-grained emotion intervention in a single per-step update: hidden space steering shifts generation along the target emotion direction, while mel-space guidance refines spectral details through gradients backpropagated from a differentiable vocoder. We validate DUET on five architecturally diverse pretrained TTS backbones across three datasets, where it outperforms 10 supervised state-of-the-art emotional TTS baselines across paradigms and achieves the highest human-rated emotion appropriateness. To further showcase its qualitative behavior, we deploy DUET on an Ameca humanoid robot, where it produces richly expressive emotional speech on the humanoid, demonstrating the strong potential for plug-and-play affective interaction for embodied agents.

Radio Environment Maps (REMs) have the potential to serve as an important enabler for intelligent modeling and control in emerging AI-native 6G networks. Despite significant progress, most REM construction methods remain passive, relying on interpolation or static uncertainty models and lacking an explicit mechanism to reason about how future measurements will affect reconstruction quality under a limited measurement budget. In this paper, we formulate REM construction as a sequential decision-making problem and propose a world-model-inspired framework for active Received Signal Strength Indicator (RSSI) map reconstruction. By learning an internal representation of the radio environment and employing a dreaming mechanism to simulate the impact of candidate measurements, the proposed approach actively selects measurement locations under a limited budget. Experimental results on real indoor RSSI data demonstrate that the proposed method significantly outperforms Gaussian Process-based interpolation in the few-shot regime, achieving up to a fivefold reduction in Root Mean Square Error (RMSE) with the same number of measurements. These results highlight the potential of world models as a powerful paradigm for sample-efficient radio environment mapping and intelligent model-based sensing in 6G and beyond networks.

The synergistic interpretation of anatomical information from computed tomography (CT) and metabolic information from positron emission tomography (PET) is important to oncologic imaging. However, existing deep learning methods for PET/CT remain largely task-specific, are often trained on single-center cohorts, or adopt dual-branch fusion schemes that delay cross-modal interaction and underutilize early spatial correspondence between PET and CT. To address these limitations, we present an open-source, multi-center, whole-body FDG PET/CT foundation model utilizing 4,997 harmonized scans from four public datasets. Our framework employs hierarchical UNet-shaped backbones with early channel-wise concatenation, enabling anatomical and metabolic features to interact from the first embedding layer onward. We further introduce a masked autoencoding objective based on zero-mean imputation, combined with a weighted global reconstruction loss. This design avoids non-physical intensity discontinuities at masked-region boundaries that arise from learnable mask tokens. On downstream AutoPET lesion segmentation, the proposed models demonstrate strong label efficiency: with only 10% of the labeled training data, they achieve performance comparable to models trained from scratch on the full dataset. Under extreme 5-shot linear probing, joint PET/CT pretraining also achieves higher Dice scores than separated-modality pretraining. This multi-center foundation model demonstrates label efficiency and cross-modality representation learning for PET/CT tumor segmentation. It provides a robust, open-source basis for advancing automated oncologic imaging, significantly reducing the need for large-scale manual annotations in clinical practice.

Beamforming has proven to be valuable in enabling full-duplex massive MIMO base stations, but doing so effectively often requires knowledge of the self-interference channel matrix H. Estimating this high-dimensional channel is costly in practice, however, since it requires a prohibitive number of measurements, especially in fast-fading conditions. In this work, we overcome this dilemma by designing full-duplex beams using implicit channel knowledge gathered from a relatively small number of measurements across H. These measurements are collected by the base station using a sequence of beams tailored to both the deployment environment and the particular users being served. This is accomplished through site-specific training of a transformer-based deep learning model that learns to efficiently probe portions of H most relevant to the particular users being served by exploiting the underlying structure of the surrounding environment. The deep learning model then uses these probing measurements to design transmit and receive beams that couple low self-interference while delivering high gain to a pair of downlink and uplink users. For favorable multi-user scaling, a single set of probing measurements can be used by the model to serve several users throughout the coherence time of H by leveraging correlations across those users' channels. Simulation results using ray-tracing demonstrate that our proposed approach exceeds the best possible performance with explicit channel estimation across a wide range of scenarios, especially with large antenna arrays.

Near-field beamfocusing enabled by extremely large-aperture arrays (ELAA) is a promising 6G technique for massive connectivity and high spectrum efficiency. While beamfocusing concentrates energy at an intended user, the radiated field outside the focal point exhibits a structured leakage that varies with the focal-point coordinates. This paper shows that this leakage enables a new form of passive user localization in which distributed far-field sensors measuring only received power can infer the user's location by exploiting this location-dependent power signature. Using the induced noncentral chi-square statistics, we derive a Bayesian Cramér-Rao lower bound (BCRLB) that establishes the fundamental limits of this inference problem. We then evaluate a model-based grid-search estimator and an attention-based permutation-invariant deep learning regressor (DeepSet). Results under both line-of-sight (LoS) and multipath propagation confirm that reliable location inference is feasible, with accuracy improving as more sensors and snapshots are used.

Field-scale crop maps support supply-chain forecasting and policy, yet statewide crop identification still often depends on retrospective surveys or remote-sensing workflows built around hand-engineered spectral features. Those pipelines can be accurate, but they require repeated preprocessing and often lose robustness across years. This study evaluated whether Google DeepMind's AlphaEarth geospatial embeddings can serve as an analysis-ready alternative for mapping processing tomato systems in California. LandIQ 2018 crop polygons were used to assemble a balanced reference dataset of 4,742 tomato and 4,742 non-tomato fields. For each polygon, 64-band AlphaEarth embedding chips were extracted and aligned with binary masks, then divided into spatially independent training (n = 6,638), validation (n = 1,422), and test (n = 1,424) sets. A U-Net segmentation model was trained on AWS SageMaker using a composite masked binary cross-entropy and soft Dice loss. To complement hard predictions, Monte Carlo dropout was retained at inference and repeated 100 times per chip to estimate predictive mean and variance. On the independent test set, the model achieved 99.19% pixel accuracy, 98.69% precision, 99.40% recall, 99.04% F1 score, 98.11% intersection over union, and 99.02% chip accuracy. Uncertainty maps were consistently highest near field edges and low within field interiors. The results show that AlphaEarth embeddings retain crop-relevant spatial and temporal structure and can support accurate, field-scale tomato mapping without manual feature engineering.

Purpose: Diffusion MRI (dMRI) provides a diverse set of quantitative measures and derived datatypes to assess white matter microstructure and macrostructure. Coupled with the increasing size of imaging studies using dMRI, the number of downstream outputs requiring quality control (QC) will continue to grow. Previous work has shown that failure modes which are often not evident from aggregate metrics or summary statistics can be identified through structured visual inspection. This work aims to better understand common failure modes and the expected characteristics of valid dMRI processing outputs to ensure the validity and interpretability of quantitative findings. Approach: We deployed a structured QC framework to assess 18,328 dMRI scans across nine datasets, visually evaluating the outputs of seven processing pipelines representative of conventional dMRI analyses. Results: Downstream outputs that pass visual QC may still rely on failed upstream dependencies; such failures may only be visually detectable through systematic inspection of the full pipeline hierarchy. Additionally, appropriate QC granularity is algorithm-specific, as the spatial structure of each algorithm's outputs determines whether failures warrant selective or global exclusion. Conclusion: This work demonstrates the feasibility and analytical value of large-scale, structured QC for dMRI processing pipelines. Our results highlight the need for systematic QC spanning the full processing hierarchy to ensure the validity and interpretability of quantitative findings.

Advanced air mobility operations will require reliable coordination mechanisms for managing dense traffic near vertiports. However, sequencing decisions may become vulnerable when they rely on potentially falsified self-reported information such as estimated time of arrival. Self-interested vehicles may misreport their arrival times to obtain favorable landing priority, while malicious actors may spoof information to disrupt sequencing decisions or induce unnecessary congestion. This paper studies secure coordination for vertiport sequencing under sensing uncertainty. We consider a coordinator that combines self-reported Remote-ID information with externally obtained surveillance measurements to check reports and assign separation-feasible arrival schedules. Since surveillance-based estimates are uncertain, falsified reports may remain consistent with the sensing uncertainty region and cannot always be rejected outright. We therefore formulate sequencing as a robust design problem over this uncertainty region. Self-interested misreporting is modeled as a strategic deviation that improves the reporting vehicle's own sequencing outcome, whereas malicious spoofing is modeled as an adversarial disturbance that degrades the system-level objective. The final paper will develop robust sequencing rules over surveillance-consistent uncertainty sets and evaluate their performance in representative vertiport sequencing scenarios.